(Article of periodic en Anglais - 2013)

Document title

Estimating wet soil aggregate stability from easily available properties in a highly mountainous watershed

Authors(s) and Affiliation(s)

(1) Dept. of Soil Science, College of Agriculture, Vali-e-Asr Univ., Rafsanjan, IRAN, REPUBLIQUE ISLAMIQUE D'
(2) Dept. of Soil Science, College of Agriculture, Univ. of Technology, Isfahan, IRAN, REPUBLIQUE ISLAMIQUE D'
(3) Inst. of Terrestrial Ecosystems, ETH Zurich, Zürich, SUISSE


A comparison study was carried out with the purpose of verifying when the adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), generalized linear model (GLM), and multiple linear regression (MLR) models are appropriate for prediction of soil wet aggregate stability (as quantified by the mean weight diameter, MWD) in a highly mountainous watershed (Bazoft watershed, southwestern Iran). Three different sets of available data including soil properties alone, topographic attributes and vegetation index, and a combination of soil properties and topographic and vegetation attributes were used as inputs. Discussions of advantages and disadvantages are given in different point of view for all the methods. In conclusion, the ANN and ANFIS models showed greater potential in predicting soil aggregate stability from soil and site characteristics, whereas linear regression methods did not perform well


Article of periodic

published at : Catena / ISSN 0341-8162

Editor : Catena, Cremlingen-Destedt - ALLEMAGNE (1973)

Millesime : 2013, vol. 111 [pp. 72-79]

Bibliographic references : 39 ref.

Collation : 4 fig., 5 tabl.



INIST-CNRS, Cote INIST : 16767

Digital Object Identifier

Go to electronic document thanks to its DOI : doi:10.1016/j.catena.2013.07.001

Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI), 2013
Refdoc record number (ud4) : 28016515 : Permanent link - XML version
Powered by Pxxo